Proton Nutzer
My feedback
4 results found
-
364 votesProton Nutzer
supported this idea
·
-
425 votesProton Nutzer
supported this idea
·
An error occurred while saving the comment -
648 votesProton Nutzer
supported this idea
·
An error occurred while saving the comment Proton Nutzer
commented
Not only proton apps.
I want to control other apps on my phone with Lumo too.
.
And yes, those features definatelly should be OptIn per App.
-
77 votes
An error occurred while saving the comment Proton Nutzer
commented
Even for the use on iPhones the local STT does not cut it,
becase you loose alle the information that is carried by your intonation (you even loose the interpunctuation).
Also if the STT is done locally, Lumo cannot adjust to your dialect and speech patters (the things we're trying to keep out of the hands of the data brokers)..
On the reverse path, having to use the local TTS ist just a bad joke.
I want to have a proper conversation with Lumo, without having to press a button to read the answers.
So instead of just the "microphone STT button" and a "read replies TTS button", an additional selector should be there,
something like a "conversation toggle switch", that activates both, until you turn it off..
And i.e. when replying by voice,
Lumo should not just read what's on the screen, cuz. if lumo starts reading a table, that does not carry very well in speech.
So Lumo should point you to the full table in the chat, but curate what it replies for the auditive communication channel.Proton Nutzer
supported this idea
·
Well, first of all, the features you seek are already there:
1.: Lumo remembers the facts of all the chats that are currently open.
2.: You can put a file into the project folder, that contains the most important informations or results you had till now and then have Lumo load this file at the beginning of each project chat.
You can also create files to special topics and load those when needed.
There are two GREAT benefits of the described method:
a. you have full control over your information, which REALLY is a difference to data hogging AIs.
b. as Lumo is not filled with random and often unimportant "memories", it is much more precise than i.e. ChatGPT.
.
I actually MUCH prefer the method described above,
over other AI randomly storing things.
Cuz the issue with other AIs is,
that they decide what's important, but that may not really be important to you.
So at some point they think they know you and their picture of you may be close,
but actually it is skew, which is why they feel strange.
And as it's all done in the background you have no influence on that.
.
Hence why, if Lumo gets a persistant memory it should adher to the following principles:
1. Lumo should ask you if it should store the post / the chat / this information.
2. It's memory should be in a form like lumo would write it.
3. The user should be able to access and edit this memory.
4. This feature should be toggleable.
5. The current functionalities MUST not get lost. *a
.
*a: The current way it works must not get lost, cuz while it's a concious effort to give Lumo a long term memory, it's what makes Lumo unique.
Because the careful curation of Lumos memory, is what makes it so precise.
Quite in difference to other AI.